github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8654] Available memory check should be disabled when mmap is in use #31368

New Issue
Open
opened 2026-04-22 11:46:08 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-22 11:46:08 -05:00
Owner
Copy Link

Originally created by @outis151 on GitHub (Jan 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8654

What is the issue?

With mmap enabled, a model does not need to fit in the system RAM. Therefore the associated check should be disabled in this case.

OS

Linux

GPU

No response

CPU

Intel

Ollama version

0.5.7

Originally created by @outis151 on GitHub (Jan 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8654 ### What is the issue? With mmap enabled, a model does not need to fit in the system RAM. Therefore the associated check should be disabled in this case. ### OS Linux ### GPU _No response_ ### CPU Intel ### Ollama version 0.5.7
GiteaMirror added the bug label 2026-04-22 11:46:08 -05:00
GiteaMirror commented 2026-04-22 11:46:09 -05:00
Author
Owner
Copy Link

@outis151 commented on GitHub (Jan 29, 2025):

In fact, deepseek-r1:671b (404 GB) is able to run on my system with only 128GB of RAM with mmap enabled if i fake the memory information to ollama.

To fake the memory information to ollama, the following systemd directive needs to be added:
BindReadOnlyPaths=/root/meminfo:/proc/meminfo
and a modified /proc/meminfo file needs to be copied to /root/meminfo

<!-- gh-comment-id:2621589918 --> @outis151 commented on GitHub (Jan 29, 2025): In fact, deepseek-r1:671b (404 GB) is able to run on my system with only 128GB of RAM with `mmap` enabled if i fake the memory information to ollama. To fake the memory information to ollama, the following systemd directive needs to be added: `BindReadOnlyPaths=/root/meminfo:/proc/meminfo` and a modified `/proc/meminfo` file needs to be copied to` /root/meminfo`
GiteaMirror commented 2026-04-22 11:46:10 -05:00
Author
Owner
Copy Link

@DrShadow34 commented on GitHub (Feb 4, 2025):

Can we bump priority on this one? I do believe that feature wise we all set to run deepseek with caching on ollama, this bug is only thing preventing it from working out of the box.

<!-- gh-comment-id:2634346442 --> @DrShadow34 commented on GitHub (Feb 4, 2025): Can we bump priority on this one? I do believe that feature wise we all set to run deepseek with caching on ollama, this bug is only thing preventing it from working out of the box.
GiteaMirror commented 2026-04-22 11:46:10 -05:00
Author
Owner
Copy Link

@Al2Klimov commented on GitHub (Feb 4, 2025):

FWIW, I helped myself with 9592dff5055b45a2a3b4cb487d4f18f247614f58

<!-- gh-comment-id:2634847315 --> @Al2Klimov commented on GitHub (Feb 4, 2025): FWIW, I helped myself with 9592dff5055b45a2a3b4cb487d4f18f247614f58
GiteaMirror commented 2026-04-22 11:46:10 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 8, 2025):

https://github.com/ollama/ollama/pull/8895

<!-- gh-comment-id:2644462057 --> @rick-github commented on GitHub (Feb 8, 2025): https://github.com/ollama/ollama/pull/8895
GiteaMirror commented 2026-04-22 11:46:11 -05:00
Author
Owner
Copy Link

@xgdgsc commented on GitHub (Feb 14, 2025):

And I feel mmap is broken in recent 2 releases. It doesn' t work like mmap, instead it loads to process memory.

<!-- gh-comment-id:2658124110 --> @xgdgsc commented on GitHub (Feb 14, 2025): And I feel mmap is broken in recent 2 releases. It doesn' t work like mmap, instead it loads to process memory.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#31368
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?